| Unit name | Applied ML for Engineering Systems |
|---|---|
| Unit code | EEME30002 |
| Credit points | 20 |
| Level of study | H/6 |
| Teaching block(s) |
Teaching Block 2 (weeks 13 - 24) |
| Unit director | Dr. Cantero Chinchilla |
| Open unit status | Not open |
| Units you must take before you take this one (pre-requisite units) |
None |
| Units you must take alongside this one (co-requisite units) |
None |
| Units you may not take alongside this one |
None |
| School/department | School of Electrical, Electronic and Mechanical Engineering |
| Faculty | Faculty of Engineering |
Why is this unit important?
Machine Learning (ML) algorithms (e.g. ChatGPT, DALL-E, etc.) are increasingly being applied to multiple domains partially due to their incredibly transforming results and computational speed. In engineering, ML methods offer a new gate providing solutions to problems that cannot be described or addressed by traditional physics-based approaches. In these cases, data is leveraged to build models capable of capturing complex and nonlinear input/output relationships. This unit will provide a comprehensive introduction to ML techniques developed and applied to complex electrical and electronic engineering problems (e.g. power systems: smart grid load forecasting, fault detection, predictive maintenance; communications: signal detection, channel equalisation, adaptive modulation, resource management, O-RAN control; control systems: adaptive and optimal control, system identification and modelling; multimedia computing: coding, compression, upscaling; computer vision; machine learning for tiny embedded systems). The unit will give you the foundations to further use, develop and appraise ML techniques. It will help you gain key skills for both the industrial and academic world in a transformative and definitive manner.
How does this unit fit into your programme of study?
This unit is mandatory on your programme of studies.
An overview of content
The unit introduces a series of data-driven ML techniques that are critical to solving some contemporary engineering problems that cannot be otherwise addressed using traditional engineering approaches. The main objective is to be able to compare, select, and apply the most appropriate technique that is fit for a target application. The unit will begin with an overview of ML techniques that offer a great degree of flexibility to solve complex engineering problems. These techniques include a variety of neural networks, e.g. fully connected and convolutional neural networks. The methods will be illustrated with relevant examples on power systems, communications, control systems, multimedia computing and embedded systems. The unit also discusses suitable optimisation approaches for determining the optimal ML model hyper-parameters.
How will students, personally, be different as a result of the unit
You will gain confidence and in-depth understanding of a series of ML techniques and when best to use them in order to solve a given engineering problem. You will experience the power of ML in processing highly complex and nonlinear data. You will understand that there is no universal solution for contemporary engineering problems despite the potential of ML. You will be able to statistically analyse datasets in order to determine whether a data-driven ML approach will work. You will be able to critically evaluate the best ML technique fit for the purpose.
Learning Outcomes
Having completed this unit, you will be able to:
A blend of live lectures and pre-recorded asynchronous videos will be used to cover the content of the unit. The independent study of the problem sheets is accompanied by the drop-in sessions with continuous feedback.
Tasks which help you learn and prepare you for summative tasks (formative):
During the course of the unit, you will be able to attend regular worked example synchronous on-campus sessions. Worksheets will be provided to give you the opportunity to practice your skills of implementing ML models independently. A Q&A online platform will be established to provide you with feedback about any questions you may have. These activities will contribute to your preparation for the unit’s summative assessment.
Tasks which count towards your unit mark (summative):
This unit will be assessed by an individual coursework submission comprising ML model code and associated documentation, and a written report with model evaluation results. The coursework will assess all Learning Outcomes.
When assessment does not go to plan:
Re-assessment takes the same form as the original summative assessment.
If this unit has a Resource List, you will normally find a link to it in the Blackboard area for the unit. Sometimes there will be a separate link for each weekly topic.
If you are unable to access a list through Blackboard, you can also find it via the Resource Lists homepage. Search for the list by the unit name or code (e.g. EEME30002).
How much time the unit requires
Each credit equates to 10 hours of total student input. For example a 20 credit unit will take you 200 hours
of study to complete. Your total learning time is made up of contact time, directed learning tasks,
independent learning and assessment activity.
See the University Workload statement relating to this unit for more information.
Assessment
The assessment methods listed in this unit specification are designed to enable students to demonstrate the named learning outcomes (LOs). Where a disability prevents a student from undertaking a specific method of assessment, schools will make reasonable adjustments to support a student to demonstrate the LO by an alternative method or with additional resources.
The Board of Examiners will consider all cases where students have failed or not completed the assessments required for credit.
The Board considers each student's outcomes across all the units which contribute to each year's programme of study. For appropriate assessments, if you have self-certificated your absence, you will normally be required to complete it the next time it runs (for assessments at the end of TB1 and TB2 this is usually in the next re-assessment period).
The Board of Examiners will take into account any exceptional circumstances and operates
within the Regulations and Code of Practice for Taught Programmes.
